ATTENTION/WARNING - NE PAS DÉPOSER ICI/DO NOT SUBMIT HERE

Ceci est la version de TEST de DIAL.mem. Veuillez ne pas soumettre votre mémoire sur ce site mais bien à l'URL suivante: 'https://thesis.dial.uclouvain.be'.
This is the TEST version of DIAL.mem. Please use the following URL to submit your master thesis: 'https://thesis.dial.uclouvain.be'.
 

Predicting the return and volatility of cryptoassets using Machine Learning

Coco, Alessandro
(2022)

Files

Coco_91392000_2022.pdf
  • Open access
  • Adobe PDF
  • 1.1 MB
Download
Coco_91392000_2022_Annexe1.pdf
  • Open access
  • Adobe PDF
  • 11.46 MB
Download

Details

Supervisors
Petitjean, Mikael ; Desagre, Christophe
Faculty
Louvain School of Management
Degree label
Master [120] : ingénieur de gestion, à finalité spécialisée
Abstract
Recently, the interest for artificial intelligence, and more specifically for Machine Learning, has been constantly growing. This method, which has the advantage of being able to self-learn, but also to analyze large amount of data in a short time, is progressively becoming widely used in large companies. Indeed, they apply this approach to enable solving complex problems as well as helping them in decision-making. In parallel, recent events such as the massive purchase of Bitcoin by several countries and global firms have created a craze around cryptocurrencies. In this dissertation, we will relate these two elements by predicting the price of ten cryptoassets using Machine Learning techniques. The results of this analysis show that linear regression, gradient boosting and random forest are the most suitable algorithms to predict the price of cryptocurrencies. We will also demonstrate that it is possible to outperform buy-and-hold approaches using momentum investing based strategies.